Abstract
Wheeled mobile robots are increasingly deployed in harsh environments where dense obstacles, traps, variable terrain, soil effects, tight energy budgets, and sensor noise often deem classical navigation stacks insufficient. This paper presents a PRISMA-guided systematic review of recent work on Deep Reinforcement Learning (DRL) for wheeled ground-robot navigation in harsh environments and organizes the field via a practical six-dimensional taxonomy: environmental challenges, navigation architecture, observation modality, action strategy, action space, and learning algorithm. The taxonomy is refined through an iterative, evidence-grounded coding process on the included studies, and applied under a transparent coding protocol to support reproducible categorization. Across the literature, DRL appears both as a planner module as well as end-to-end policy (behavior) implementer tool. Regarding observation, mapless navigation based on LiDAR or cameras are prevalent. Actions are predicted mostly one time step ahead and are continuous. Actor–critic methods are prevalent, notably PPO and SAC are the common DRL methods used. As for the evaluation methodology, it remains largely simulation-based, with only limited sim-to-real protocols. Building on these findings, we use the previously mentioned taxonomy to identify common design choices for navigation in harsh terrains, propose minimum reporting practices to enable reproducible comparison, and propose research directions including energy-aware learning, improved robustness to sensor degradation, all weather soil–vehicle interaction modeling, short-horizon look-ahead for stability and smoothness, standardized tasks and metrics. The proposed taxonomy and guidelines, as well as identified trends, intend to help researchers and practitioners select methods that best suits their own objectives and constraints, thus hopefully accelerating progress from promising simulation results to dependable, field-ready autonomy. © 2013 IEEE.

Abstract
This study examines whether Parameter-Efficient Fine-Tuning (PEFT) of lightweight, free, and open-licensed Large Language Models (LLMs) can yield tutoring assistants for introductory circuit analysis methods, while fitting the students' needs. We analyzed 260 Electrical and Computer Engineering (ECE) exam responses to classify and quantify frequent students' mistakes when applying the Loop Current Method (LCM). Only 28.5% solved the target problem without error, and most difficulties were conceptual (e.g., miscounting the number of independent Kirchhoff's Voltage Law (KVL) equations). Driven by this taxonomy, we assembled official course materials and curated a bilingual (Portuguese-English) pedagogical dataset. Using GTP-4o for distillation, we generated question-answer (QA) pairs for fine-tuning smaller models (Meta Llama 3.2 1B and 3.1 8B), via Quantized Low-Rank Adaptation (QLoRA) on a single commodity GPU, with an end-to-end pipeline completing in under 7 min. A blind study involving 77 first-year ECE students evaluated responses to (never seen) questions from both our tuned models and GPT-4.5, rating correctness, clarity, educational value, task coverage, and style. The 8B model scored within one point (5-point Likert) of GPT-4.5 model and both 1B and 8B were consistently preferred over untuned baseline versions for clarity and task coverage. As a complementary cross-check, 12 higher education senior professors independently evaluated model responses, largely corroborating the student-based rankings. These results provide evidence that carefully curated documents introducing electrical circuit theory, combined with smaller models optimized with PEFT, namely QLoRA, can be used in the construction of a always-available tutoring application. The proposed system features modest cost, runs on consumer-grade hardware, and paves the way for deployable front-end applications that do not involve possibly expensive, resource-hungry, remote machines.

Abstract
The textile industry is experiencing rapid advancement, reflected in the adoption of innovative and efficient manufacturing techniques. The automation of clothing sewing systems has the potential to reduce the allocation of repetitive tasks to operators, freeing them for more value-added operations. There are several machines on the market that automatically sew the bottom hem of T-shirts, a key component of the garment that fulfills both functional and aesthetic purposes. However, most of them require the fabric to be positioned manually by an operator. To address this issue, this work presents a solution to automate the process of feeding a T-shirt into a SiRUBA sewing machine using a YuMi dual-arm robot. In this scenario, the T-shirt arrives at the workstation with the main front and back pieces of cloth sewn together, seams facing out, and with no sleeves yet. This setup starts by turning the garment inside out with the aid of an automated hanger, ensuring that the seams are facing inward (as the machine requires), and then using the dual-arm robot to feed the garment into the sewing machine. With our approach, the feeding and hemming process took less than 35 seconds, with a feeding success rate of 98%. Therefore, this work can serve as a steppingstone towards more efficient automated sewing systems within the garment production industry.

Abstract
Bringing AI models from digital to real-world applications presents significant challenges due to the complexity and variability of physical environments, often leading to unexpected model behaviors. We propose a framework that learns to translate images into control actions by modeling multimodal real-time data and system dynamics. This end-to-end controller offers enhanced explainability and robustness, making it well suited for complex manufacturing processes. This end-to-end framework differs from traditional approaches that rely on manually engineered features by learning complex relationships directly from raw data. Labels are only required during training to define the observable feature to be optimized. This adaptability significantly reduces development time and enhances scalability across varying conditions. This approach was tested in the Directed Energy Deposition (L-DED) process, a laser-based metal additive manufacturing technique that produces near-net-shape parts with exceptional energy efficiency and flexibility in both geometry and material selection. L-DED is inherently complex, involving multiphysics interactions, multiscale phenomena, and dynamic behaviors, which make modeling and optimization difficult. Effective control is crucial to ensure part quality in this dynamic environment. To address these challenges, we introduce Joint Embedding Multimodal Alignment with Sparse Identification of Nonlinear Dynamics for control (JEMA-SINDYc). It combines an image-based JEMA monitoring model, which predicts the melt pool size using only the on-axis sensor with labels provided by the off-axis camera, and dynamic modeling using SINDYc, which acts as a World Model by capturing system dynamics within the embedding space. Together, these components enable the development of an advanced controller trained via Behavioral Cloning. This approach improves part quality by minimizing porosity and reducing deformation. Thin-walled cylindrical parts were produced to validate and compare this approach with other control strategies, including both open-loop and JEMA-PID. This framework improves the reliability of AI-driven manufacturing and enhances control of complex industrial processes, potentially enabling wider adoption of the process.

Abstract
Engineering is considered important in solving unsustainability. However, it is a complex problem that must be viewed, analysed and studied from various perspectives and taking with the contribution of various areas of knowledge. This work studied the use of interdisciplinarity as a contribution to interconnect ethics and sustainability with technical-scientific contents of electrical engineering. The research intended to use interdisciplinarity to help engineering students recognise that engineering is not ethically neutral, and that, therefore, the problems (and solutions) must also be analysed from an ethical and sustainability perspective. A framework was developed, and a pedagogical activity using interdisciplinarity was applied. Results show that, after the activity, students recognise that ethical values influence calculations in the area of electrical installations; and move from a single view to identify different alternatives, perspectives, motivations and multiple objectives. This leads to studying more alternatives and hopefully better overall technical solutions.